SOURCE-LINKED INTELLIGENCE

PersonaEdit: Representative Sample Selection for Personalized Model Editing

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifies internal model parameters to incorporate new knowledge, has demonstrated effective knowledge modification capabilities in factual knowledge editing tasks and may provide a potential solution for personalization. However, scaling model editing to personalization is non-trivial. Editing large amounts of user data increases computational cost and causes interference among edits,

Read original source ↗ Open in workspace

recordType

paper

region

Global